Create app.py

app.py

@@ -0,0 +1,68 @@
+import torch
+import streamlit as st
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+import re
+import string
+
+def tokenize_sentences(sentence):
+    encoded_dict = tokenizer.encode_plus(
+        sentence,
+        add_special_tokens=True,
+        max_length=128,
+        padding='max_length',
+        truncation=True,
+        return_attention_mask=True,
+        return_tensors='pt'
+    )
+    return torch.cat([encoded_dict['input_ids']], dim=0), torch.cat([encoded_dict['attention_mask']], dim=0)
+
+ 
+
+def preprocess_query(query):
+    query = str(query).lower()
+    query = query.strip()
+    query=query.translate(str.maketrans("", "", string.punctuation))
+    return query
+
+def predict_category(sentence, threshold):
+    input_ids, attention_mask = tokenize_sentences(sentence)
+    with torch.no_grad():
+        outputs = categories_model(input_ids, attention_mask=attention_mask)
+    logits = outputs.logits
+    predicted_categories = torch.sigmoid(logits).squeeze().tolist()
+    results = dict()
+    for label, prediction in zip(LABEL_COLUMNS_CATEGORIES, predicted_categories):
+        if prediction < threshold:
+            continue
+        precentage = round(float(prediction) * 100, 2)
+        results[label] = precentage
+    return results
+
+# Load tokenizer and model
+BERT_MODEL_NAME_FOR_CATEGORIES_CLASSIFICATION = 'roberta-large'
+tokenizer = RobertaTokenizer.from_pretrained(BERT_MODEL_NAME_FOR_CATEGORIES_CLASSIFICATION, do_lower_case=True)
+
+LABEL_COLUMNS_CATEGORIES = ['AMBIENCE', 'DRINK', 'FOOD', 'GENERAL', 'RESTAURANT', 'SERVICE', 'STAFF']
+
+categories_model = RobertaForSequenceClassification.from_pretrained(BERT_MODEL_NAME_FOR_CATEGORIES_CLASSIFICATION, num_labels=len(LABEL_COLUMNS_CATEGORIES))
+categories_model.load_state_dict(torch.load('./Categories_Classification_Model_updated.pth'))
+categories_model.eval()
+
+# Streamlit App
+st.title("Review/Sentence Classification")
+st.write("Multilable/Multiclass Sentence classification under 7 Defined Categories. ")
+
+sentence = st.text_input("Enter a sentence:")
+threshold = st.slider("Threshold", min_value=0.0, max_value=1.0, step=0.01, value=0.5)
+
+if sentence:
+    processed_sentence = preprocess_query(sentence)
+    results = predict_category(processed_sentence, threshold)
+    if len(results) > 0:
+        st.write("Predicted Aspects:")
+        table_data = [["Category", "Probability"]]
+        for category, percentage in results.items():
+            table_data.append([category, f"{percentage}%"])
+        st.table(table_data)
+    else:
+        st.write("No Categories above the threshold.")